Training in progress, step 46500

nohup.out

@@ -25526,3 +25526,275 @@ Configuration saved in ./checkpoint-46000/config.json
 Model weights saved in ./checkpoint-46000/pytorch_model.bin
 Configuration saved in ./checkpoint-46000/preprocessor_config.json
 Configuration saved in ./preprocessor_config.json
+Deleting older checkpoint [checkpoint-44500] due to args.save_total_limit
+
 68%|██████▊   | 46001/67700 [27:41:19<366:06:59, 60.74s/it]
 68%|██████▊   | 46002/67700 [27:41:20<258:33:13, 42.90s/it]
 68%|██████▊   | 46003/67700 [27:41:21<183:13:30, 30.40s/it]
 68%|██████▊   | 46004/67700 [27:41:22<130:25:38, 21.64s/it]
 68%|██████▊   | 46005/67700 [27:41:23<93:26:44, 15.51s/it] 
 68%|██████▊   | 46006/67700 [27:41:25<67:35:30, 11.22s/it]
 68%|██████▊   | 46007/67700 [27:41:26<49:08:57,  8.16s/it]
 68%|██████▊   | 46008/67700 [27:41:27<36:04:45,  5.99s/it]
 68%|██████▊   | 46009/67700 [27:41:28<27:01:06,  4.48s/it]
 68%|██████▊   | 46010/67700 [27:41:30<23:33:15,  3.91s/it]
 68%|██████▊   | 46011/67700 [27:41:33<21:01:25,  3.49s/it]
 68%|██████▊   | 46012/67700 [27:41:35<19:04:40,  3.17s/it]
 68%|██████▊   | 46013/67700 [27:41:37<17:27:24,  2.90s/it]
 68%|██████▊   | 46014/67700 [27:41:40<16:14:16,  2.70s/it]
 68%|██████▊   | 46015/67700 [27:41:42<15:19:57,  2.55s/it]
 68%|██████▊   | 46016/67700 [27:41:44<14:35:15,  2.42s/it]
 68%|██████▊   | 46017/67700 [27:41:46<14:05:05,  2.34s/it]
 68%|██████▊   | 46018/67700 [27:41:48<13:38:50,  2.27s/it]
 68%|██████▊   | 46019/67700 [27:41:50<13:14:29,  2.20s/it]
 68%|██████▊   | 46020/67700 [27:41:52<12:48:10,  2.13s/it]
 68%|██████▊   | 46021/67700 [27:41:54<12:24:31,  2.06s/it]
 68%|██████▊   | 46022/67700 [27:41:56<11:57:26,  1.99s/it]
 68%|██████▊   | 46023/67700 [27:41:58<11:44:13,  1.95s/it]
 68%|██████▊   | 46024/67700 [27:41:59<11:23:12,  1.89s/it]
 68%|██████▊   | 46025/67700 [27:42:01<11:03:34,  1.84s/it]
 68%|██████▊   | 46026/67700 [27:42:03<10:42:41,  1.78s/it]
 68%|██████▊   | 46027/67700 [27:42:04<10:28:00,  1.74s/it]
 68%|██████▊   | 46028/67700 [27:42:06<10:10:39,  1.69s/it]
 68%|██████▊   | 46029/67700 [27:42:08<9:48:54,  1.63s/it] 
 68%|██████▊   | 46030/67700 [27:42:09<9:27:56,  1.57s/it]
 68%|██████▊   | 46031/67700 [27:42:10<9:13:40,  1.53s/it]
 68%|██████▊   | 46032/67700 [27:42:12<8:54:06,  1.48s/it]
 68%|██████▊   | 46033/67700 [27:42:13<8:30:36,  1.41s/it]
 68%|██████▊   | 46034/67700 [27:42:14<8:08:13,  1.35s/it]
 68%|██████▊   | 46035/67700 [27:42:15<7:42:42,  1.28s/it]
 68%|██████▊   | 46036/67700 [27:42:16<7:14:02,  1.20s/it]
 68%|██████▊   | 46037/67700 [27:42:19<10:05:18,  1.68s/it]
 68%|██████▊   | 46038/67700 [27:42:22<11:43:41,  1.95s/it]
 68%|██████▊   | 46039/67700 [27:42:24<12:40:26,  2.11s/it]
 68%|██████▊   | 46040/67700 [27:42:27<13:20:45,  2.22s/it]
 68%|██████▊   | 46041/67700 [27:42:29<13:36:25,  2.26s/it]
 68%|██████▊   | 46042/67700 [27:42:31<13:38:15,  2.27s/it]
 68%|██████▊   | 46043/67700 [27:42:34<13:45:34,  2.29s/it]
 68%|██████▊   | 46044/67700 [27:42:36<13:42:04,  2.28s/it]
 68%|██████▊   | 46045/67700 [27:42:38<13:40:19,  2.27s/it]
 68%|██████▊   | 46046/67700 [27:42:40<13:35:21,  2.26s/it]
 68%|██████▊   | 46047/67700 [27:42:43<13:18:40,  2.21s/it]
 68%|██████▊   | 46048/67700 [27:42:45<13:07:35,  2.18s/it]
 68%|██████▊   | 46049/67700 [27:42:47<12:54:26,  2.15s/it]
 68%|██████▊   | 46050/67700 [27:42:49<12:45:19,  2.12s/it]
 68%|██████▊   | 46051/67700 [27:42:51<12:34:59,  2.09s/it]
 68%|██████▊   | 46052/67700 [27:42:53<12:27:18,  2.07s/it]
 68%|██████▊   | 46053/67700 [27:42:55<12:16:19,  2.04s/it]
 68%|██████▊   | 46054/67700 [27:42:57<12:08:37,  2.02s/it]
 68%|██████▊   | 46055/67700 [27:42:59<11:57:35,  1.99s/it]
 68%|██████▊   | 46056/67700 [27:43:01<11:47:42,  1.96s/it]
 68%|██████▊   | 46057/67700 [27:43:02<11:36:11,  1.93s/it]
 68%|██████▊   | 46058/67700 [27:43:04<11:30:05,  1.91s/it]
 68%|██████▊   | 46059/67700 [27:43:06<11:20:20,  1.89s/it]
 68%|██████▊   | 46060/67700 [27:43:08<11:13:45,  1.87s/it]
 68%|██████▊   | 46061/67700 [27:43:10<11:00:41,  1.83s/it]
 68%|██████▊   | 46062/67700 [27:43:11<10:51:27,  1.81s/it]
 68%|██████▊   | 46063/67700 [27:43:13<10:43:59,  1.79s/it]
 68%|██████▊   | 46064/67700 [27:43:15<10:33:46,  1.76s/it]
 68%|██████▊   | 46065/67700 [27:43:17<10:24:08,  1.73s/it]
 68%|██████▊   | 46066/67700 [27:43:18<10:13:57,  1.70s/it]
 68%|██████▊   | 46067/67700 [27:43:20<10:01:12,  1.67s/it]
 68%|██████▊   | 46068/67700 [27:43:21<9:53:12,  1.65s/it] 
 68%|██████▊   | 46069/67700 [27:43:23<9:40:56,  1.61s/it]
 68%|██████▊   | 46070/67700 [27:43:24<9:34:47,  1.59s/it]
 68%|██████▊   | 46071/67700 [27:43:26<9:25:13,  1.57s/it]
 68%|██████▊   | 46072/67700 [27:43:27<9:15:11,  1.54s/it]
 68%|██████▊   | 46073/67700 [27:43:29<9:07:54,  1.52s/it]
 68%|██████▊   | 46074/67700 [27:43:30<9:02:00,  1.50s/it]
 68%|██████▊   | 46075/67700 [27:43:32<8:58:03,  1.49s/it]
 68%|██████▊   | 46076/67700 [27:43:33<8:45:34,  1.46s/it]
 68%|██████▊   | 46077/67700 [27:43:35<8:37:03,  1.43s/it]
 68%|██████▊   | 46078/67700 [27:43:36<8:25:02,  1.40s/it]
 68%|██████▊   | 46079/67700 [27:43:37<8:17:10,  1.38s/it]
 68%|██████▊   | 46080/67700 [27:43:38<8:02:06,  1.34s/it]
 68%|██████▊   | 46081/67700 [27:43:40<7:48:01,  1.30s/it]
 68%|██████▊   | 46082/67700 [27:43:41<7:43:26,  1.29s/it]
 68%|██████▊   | 46083/67700 [27:43:42<7:31:36,  1.25s/it]
 68%|██████▊   | 46084/67700 [27:43:43<7:19:33,  1.22s/it]
 68%|██████▊   | 46085/67700 [27:43:44<6:56:03,  1.15s/it]
 68%|██████▊   | 46086/67700 [27:43:45<6:34:59,  1.10s/it]
 68%|██████▊   | 46087/67700 [27:43:48<9:17:46,  1.55s/it]
 68%|██████▊   | 46088/67700 [27:43:50<11:07:42,  1.85s/it]
 68%|██████▊   | 46089/67700 [27:43:53<12:15:44,  2.04s/it]
 68%|██████▊   | 46090/67700 [27:43:55<13:02:09,  2.17s/it]
 68%|██████▊   | 46091/67700 [27:43:58<13:23:43,  2.23s/it]
 68%|██████▊   | 46092/67700 [27:44:00<13:31:47,  2.25s/it]
 68%|██████▊   | 46093/67700 [27:44:02<13:31:38,  2.25s/it]
 68%|██████▊   | 46094/67700 [27:44:05<13:38:22,  2.27s/it]
 68%|██████▊   | 46095/67700 [27:44:07<13:29:25,  2.25s/it]
 68%|██████▊   | 46096/67700 [27:44:09<13:21:36,  2.23s/it]
 68%|██████▊   | 46097/67700 [27:44:11<13:13:19,  2.20s/it]
 68%|██████▊   | 46098/67700 [27:44:13<13:06:36,  2.18s/it]
 68%|██████▊   | 46099/67700 [27:44:15<12:52:49,  2.15s/it]
 68%|██████▊   | 46100/67700 [27:44:17<12:44:24,  2.12s/it]
                                                           
 68%|██████▊   | 46100/67700 [27:44:17<12:44:24,  2.12s/it]
 68%|██████▊   | 46101/67700 [27:44:19<12:35:34,  2.10s/it]
 68%|██████▊   | 46102/67700 [27:44:21<12:31:15,  2.09s/it]
 68%|██████▊   | 46103/67700 [27:44:24<12:23:53,  2.07s/it]
 68%|██████▊   | 46104/67700 [27:44:25<12:13:21,  2.04s/it]
 68%|██████▊   | 46105/67700 [27:44:27<11:57:21,  1.99s/it]
 68%|██████▊   | 46106/67700 [27:44:29<11:45:59,  1.96s/it]
 68%|██████▊   | 46107/67700 [27:44:31<11:31:51,  1.92s/it]
 68%|██████▊   | 46108/67700 [27:44:33<11:25:38,  1.91s/it]
 68%|██████▊   | 46109/67700 [27:44:35<11:09:43,  1.86s/it]
 68%|██████▊   | 46110/67700 [27:44:37<11:01:35,  1.84s/it]
 68%|██████▊   | 46111/67700 [27:44:38<10:53:22,  1.82s/it]
 68%|██████▊   | 46112/67700 [27:44:40<10:46:29,  1.80s/it]
 68%|██████▊   | 46113/67700 [27:44:42<10:38:30,  1.77s/it]
 68%|██████▊   | 46114/67700 [27:44:43<10:27:34,  1.74s/it]
 68%|██████▊   | 46115/67700 [27:44:45<10:15:42,  1.71s/it]
 68%|██████▊   | 46116/67700 [27:44:47<10:12:36,  1.70s/it]
 68%|██████▊   | 46117/67700 [27:44:48<10:00:45,  1.67s/it]
 68%|██████▊   | 46118/67700 [27:44:50<9:54:55,  1.65s/it] 
 68%|██████▊   | 46119/67700 [27:44:52<9:45:21,  1.63s/it]
 68%|██████▊   | 46120/67700 [27:44:53<9:43:03,  1.62s/it]
 68%|██████▊   | 46121/67700 [27:44:55<9:29:39,  1.58s/it]
 68%|██████▊   | 46122/67700 [27:44:56<9:17:52,  1.55s/it]
 68%|██████▊   | 46123/67700 [27:44:58<9:07:08,  1.52s/it]
 68%|██████▊   | 46124/67700 [27:44:59<9:00:17,  1.50s/it]
 68%|██████▊   | 46125/67700 [27:45:00<8:49:25,  1.47s/it]
 68%|██████▊   | 46126/67700 [27:45:02<8:40:50,  1.45s/it]
 68%|██████▊   | 46127/67700 [27:45:03<8:32:18,  1.42s/it]
 68%|██████▊   | 46128/67700 [27:45:05<8:22:54,  1.40s/it]
 68%|██████▊   | 46129/67700 [27:45:06<8:10:33,  1.36s/it]
 68%|██████▊   | 46130/67700 [27:45:07<7:59:37,  1.33s/it]
 68%|██████▊   | 46131/67700 [27:45:08<7:46:50,  1.30s/it]
 68%|██████▊   | 46132/67700 [27:45:09<7:35:53,  1.27s/it]
 68%|██████▊   | 46133/67700 [27:45:11<7:35:35,  1.27s/it]
 68%|██████▊   | 46134/67700 [27:45:12<7:16:34,  1.21s/it]
 68%|██████▊   | 46135/67700 [27:45:13<6:47:09,  1.13s/it]
 68%|██████▊   | 46136/67700 [27:45:14<6:18:45,  1.05s/it]
 68%|██████▊   | 46137/67700 [27:45:16<9:03:27,  1.51s/it]
 68%|██████▊   | 46138/67700 [27:45:19<11:01:34,  1.84s/it]
 68%|██████▊   | 46139/67700 [27:45:21<12:16:45,  2.05s/it]
 68%|██████▊   | 46140/67700 [27:45:24<12:58:34,  2.17s/it]
 68%|██████▊   | 46141/67700 [27:45:26<13:24:04,  2.24s/it]
 68%|██████▊   | 46142/67700 [27:45:29<13:33:54,  2.27s/it]
 68%|██████▊   | 46143/67700 [27:45:31<13:34:10,  2.27s/it]
 68%|██████▊   | 46144/67700 [27:45:33<13:25:57,  2.24s/it]
 68%|██████▊   | 46145/67700 [27:45:35<13:20:49,  2.23s/it]
 68%|██████▊   | 46146/67700 [27:45:37<13:15:27,  2.21s/it]
 68%|██████▊   | 46147/67700 [27:45:39<13:05:29,  2.19s/it]
 68%|██████▊   | 46148/67700 [27:45:42<12:58:32,  2.17s/it]
 68%|██████▊   | 46149/67700 [27:45:44<12:51:25,  2.15s/it]
 68%|██████▊   | 46150/67700 [27:45:46<12:46:19,  2.13s/it]
 68%|██████▊   | 46151/67700 [27:45:48<12:39:53,  2.12s/it]
 68%|██████▊   | 46152/67700 [27:45:50<12:40:15,  2.12s/it]
 68%|██████▊   | 46153/67700 [27:45:52<12:29:54,  2.09s/it]
 68%|██████▊   | 46154/67700 [27:45:54<12:15:55,  2.05s/it]
 68%|██████▊   | 46155/67700 [27:45:56<12:04:22,  2.02s/it]
 68%|██████▊   | 46156/67700 [27:45:58<11:49:15,  1.98s/it]
 68%|██████▊   | 46157/67700 [27:46:00<11:32:51,  1.93s/it]
 68%|██████▊   | 46158/67700 [27:46:01<11:20:26,  1.90s/it]
 68%|██████▊   | 46159/67700 [27:46:03<11:11:28,  1.87s/it]
 68%|██████▊   | 46160/67700 [27:46:05<11:10:55,  1.87s/it]
 68%|██████▊   | 46161/67700 [27:46:07<11:00:49,  1.84s/it]
 68%|██████▊   | 46162/67700 [27:46:09<10:51:15,  1.81s/it]
 68%|██████▊   | 46163/67700 [27:46:10<10:45:43,  1.80s/it]
 68%|██████▊   | 46164/67700 [27:46:12<10:33:59,  1.77s/it]
 68%|██████▊   | 46165/67700 [27:46:14<10:24:03,  1.74s/it]
 68%|██████▊   | 46166/67700 [27:46:15<10:12:52,  1.71s/it]
 68%|██████▊   | 46167/67700 [27:46:17<10:00:59,  1.67s/it]
 68%|██████▊   | 46168/67700 [27:46:19<9:51:19,  1.65s/it] 
 68%|██████▊   | 46169/67700 [27:46:20<9:45:58,  1.63s/it]
 68%|██████▊   | 46170/67700 [27:46:22<9:38:21,  1.61s/it]
 68%|██████▊   | 46171/67700 [27:46:23<9:32:16,  1.59s/it]
 68%|██████▊   | 46172/67700 [27:46:25<9:22:22,  1.57s/it]
 68%|██████▊   | 46173/67700 [27:46:26<9:09:16,  1.53s/it]
 68%|██████▊   | 46174/67700 [27:46:28<9:03:00,  1.51s/it]
 68%|██████▊   | 46175/67700 [27:46:29<8:52:45,  1.49s/it]
 68%|██████▊   | 46176/67700 [27:46:31<8:42:21,  1.46s/it]
 68%|██████▊   | 46177/67700 [27:46:32<8:34:47,  1.44s/it]
 68%|██████▊   | 46178/67700 [27:46:33<8:25:33,  1.41s/it]
 68%|██████▊   | 46179/67700 [27:46:35<8:12:23,  1.37s/it]
 68%|██████▊   | 46180/67700 [27:46:36<8:01:30,  1.34s/it]
 68%|██████▊   | 46181/67700 [27:46:37<7:52:37,  1.32s/it]
 68%|██████▊   | 46182/67700 [27:46:38<7:39:18,  1.28s/it]
 68%|██████▊   | 46183/67700 [27:46:39<7:25:36,  1.24s/it]
 68%|██████▊   | 46184/67700 [27:46:41<7:13:01,  1.21s/it]
 68%|██████▊   | 46185/67700 [27:46:42<6:52:50,  1.15s/it]
 68%|██████▊   | 46186/67700 [27:46:43<6:31:51,  1.09s/it]
 68%|██████▊   | 46187/67700 [27:46:45<9:28:19,  1.59s/it]
 68%|██████▊   | 46188/67700 [27:46:48<11:14:14,  1.88s/it]
 68%|██████▊   | 46189/67700 [27:46:50<12:24:05,  2.08s/it]
 68%|██████▊   | 46190/67700 [27:46:53<13:03:38,  2.19s/it]
 68%|██████▊   | 46191/67700 [27:46:55<13:33:10,  2.27s/it]
 68%|██████▊   | 46192/67700 [27:46:58<13:48:20,  2.31s/it]
 68%|██████▊   | 46193/67700 [27:47:00<13:45:07,  2.30s/it]
 68%|██████▊   | 46194/67700 [27:47:02<13:43:42,  2.30s/it]
 68%|██████▊   | 46195/67700 [27:47:04<13:34:38,  2.27s/it]
 68%|██████▊   | 46196/67700 [27:47:07<13:26:57,  2.25s/it]
 68%|██████▊   | 46197/67700 [27:47:09<13:17:28,  2.23s/it]
 68%|██████▊   | 46198/67700 [27:47:11<13:05:05,  2.19s/it]
 68%|██████▊   | 46199/67700 [27:47:13<12:54:36,  2.16s/it]
 68%|██████▊   | 46200/67700 [27:47:15<12:44:15,  2.13s/it]
                                                           
 68%|██████▊   | 46200/67700 [27:47:15<12:44:15,  2.13s/it]
 68%|██���███▊   | 46201/67700 [27:47:17<12:33:42,  2.10s/it]
 68%|██████▊   | 46202/67700 [27:47:19<12:25:24,  2.08s/it]
 68%|██████▊   | 46203/67700 [27:47:21<12:18:37,  2.06s/it]
 68%|██████▊   | 46204/67700 [27:47:23<12:13:05,  2.05s/it]
 68%|██████▊   | 46205/67700 [27:47:25<12:01:57,  2.02s/it]
 68%|██████▊   | 46206/67700 [27:47:27<11:53:56,  1.99s/it]
 68%|██████▊   | 46207/67700 [27:47:29<11:40:12,  1.95s/it]
 68%|██████▊   | 46208/67700 [27:47:31<11:31:05,  1.93s/it]
 68%|██████▊   | 46209/67700 [27:47:33<11:19:44,  1.90s/it]
 68%|██████▊   | 46210/67700 [27:47:34<11:11:55,  1.88s/it]
 68%|██████▊   | 46211/67700 [27:47:36<11:04:12,  1.85s/it]
 68%|██████▊   | 46212/67700 [27:47:38<10:50:01,  1.82s/it]
 68%|██████▊   | 46213/67700 [27:47:40<10:37:31,  1.78s/it]
 68%|██████▊   | 46214/67700 [27:47:41<10:31:31,  1.76s/it]
 68%|██████▊   | 46215/67700 [27:47:43<10:21:09,  1.73s/it]
 68%|██████▊   | 46216/67700 [27:47:45<10:13:18,  1.71s/it]
 68%|██████▊   | 46217/67700 [27:47:46<10:04:25,  1.69s/it]
 68%|██████▊   | 46218/67700 [27:47:48<9:56:21,  1.67s/it] 
 68%|██████▊   | 46219/67700 [27:47:50<9:49:08,  1.65s/it]
 68%|██████▊   | 46220/67700 [27:47:51<9:42:52,  1.63s/it]
 68%|██████▊   | 46221/67700 [27:47:53<9:30:45,  1.59s/it]
 68%|██████▊   | 46222/67700 [27:47:54<9:26:49,  1.58s/it]
 68%|██████▊   | 46223/67700 [27:47:56<9:16:59,  1.56s/it]
 68%|██████▊   | 46224/67700 [27:47:57<9:07:03,  1.53s/it]
 68%|██████▊   | 46225/67700 [27:47:59<8:56:42,  1.50s/it]
 68%|██████▊   | 46226/67700 [27:48:00<8:48:13,  1.48s/it]
 68%|██████▊   | 46227/67700 [27:48:01<8:42:10,  1.46s/it]
 68%|██████▊   | 46228/67700 [27:48:03<8:31:49,  1.43s/it]
 68%|██████▊   | 46229/67700 [27:48:04<8:17:50,  1.39s/it]
 68%|██████▊   | 46230/67700 [27:48:05<8:02:53,  1.35s/it]
 68%|██████▊   | 46231/67700 [27:48:07<7:51:50,  1.32s/it]
 68%|██████▊   | 46232/67700 [27:48:08<7:40:00,  1.29s/it]
 68%|██████▊   | 46233/67700 [27:48:09<7:29:52,  1.26s/it]
 68%|██████▊   | 46234/67700 [27:48:10<7:17:48,  1.22s/it]
 68%|██████▊   | 46235/67700 [27:48:11<7:08:13,  1.20s/it]
 68%|██████▊   | 46236/67700 [27:48:12<6:45:04,  1.13s/it]
 68%|██████▊   | 46237/67700 [27:48:15<9:25:43,  1.58s/it]
 68%|██████▊   | 46238/67700 [27:48:18<11:13:30,  1.88s/it]
 68%|██████▊   | 46239/67700 [27:48:20<12:26:08,  2.09s/it]
 68%|██████▊   | 46240/67700 [27:48:23<13:07:12,  2.20s/it]
 68%|██████▊   | 46241/67700 [27:48:25<13:32:23,  2.27s/it]
 68%|██████▊   | 46242/67700 [27:48:27<13:36:29,  2.28s/it]
 68%|██████▊   | 46243/67700 [27:48:30<13:30:53,  2.27s/it]
 68%|██████▊   | 46244/67700 [27:48:32<13:23:06,  2.25s/it]
 68%|██████▊   | 46245/67700 [27:48:34<13:25:55,  2.25s/it]
 68%|██████▊   | 46246/67700 [27:48:36<13:14:35,  2.22s/it]
 68%|██████▊   | 46247/67700 [27:48:38<13:06:05,  2.20s/it]
 68%|██████▊   | 46248/67700 [27:48:40<13:01:39,  2.19s/it]
 68%|██████▊   | 46249/67700 [27:48:43<13:02:17,  2.19s/it]
 68%|██████▊   | 46250/67700 [27:48:45<12:51:05,  2.16s/it]
 68%|██████▊   | 46251/67700 [27:48:47<12:44:35,  2.14s/it]
 68%|██████▊   | 46252/67700 [27:48:49<12:33:17,  2.11s/it]
 68%|██████▊   | 46253/67700 [27:48:51<12:22:46,  2.08s/it]
 68%|██████▊   | 46254/67700 [27:48:53<12:22:45,  2.08s/it]
 68%|██████▊   | 46255/67700 [27:48:55<12:23:06,  2.08s/it]
 68%|██████▊   | 46256/67700 [27:48:57<12:03:25,  2.02s/it]
 68%|██████▊   | 46257/67700 [27:48:59<11:48:54,  1.98s/it]
 68%|██████▊   | 46258/67700 [27:49:01<11:37:13,  1.95s/it]
 68%|██████▊   | 46259/67700 [27:49:03<11:23:22,  1.91s/it]
 68%|██████▊   | 46260/67700 [27:49:04<11:13:11,  1.88s/it]
 68%|██████▊   | 46261/67700 [27:49:06<10:58:34,  1.84s/it]
 68%|██████▊   | 46262/67700 [27:49:08<10:53:05,  1.83s/it]
 68%|██████▊   | 46263/67700 [27:49:10<10:45:22,  1.81s/it]
 68%|██████▊   | 46264/67700 [27:49:11<10:40:02,  1.79s/it]
 68%|██████▊   | 46265/67700 [27:49:13<10:24:24,  1.75s/it]
 68%|██████▊   | 46266/67700 [27:49:15<10:14:50,  1.72s/it]
 68%|██████▊   | 46267/67700 [27:49:16<10:06:35,  1.70s/it]
 68%|██████▊   | 46268/67700 [27:49:18<9:55:51,  1.67s/it] 
 68%|██████▊   | 46269/67700 [27:49:19<9:44:42,  1.64s/it]
 68%|██████▊   | 46270/67700 [27:49:21<9:34:03,  1.61s/it]
 68%|██████▊   | 46271/67700 [27:49:23<9:35:01,  1.61s/it]
 68%|██████▊   | 46272/67700 [27:49:24<9:26:37,  1.59s/it]
 68%|██████▊   | 46273/67700 [27:49:26<9:16:33,  1.56s/it]
 68%|██████▊   | 46274/67700 [27:49:27<9:06:04,  1.53s/it]
 68%|██████▊   | 46275/67700 [27:49:29<8:53:42,  1.49s/it]
 68%|██████▊   | 46276/67700 [27:49:30<8:44:31,  1.47s/it]
 68%|██████▊   | 46277/67700 [27:49:31<8:33:33,  1.44s/it]
 68%|██████▊   | 46278/67700 [27:49:33<8:25:49,  1.42s/it]
 68%|██████▊   | 46279/67700 [27:49:34<8:11:09,  1.38s/it]
 68%|██████▊   | 46280/67700 [27:49:35<8:00:04,  1.34s/it]
 68%|██████▊   | 46281/67700 [27:49:36<7:46:00,  1.31s/it]
 68%|██████▊   | 46282/67700 [27:49:38<7:34:34,  1.27s/it]
 68%|██████▊   | 46283/67700 [27:49:39<7:23:39,  1.24s/it]
 68%|██████▊   | 46284/67700 [27:49:40<7:11:14,  1.21s/it]
 68%|██████▊   | 46285/67700 [27:49:41<6:52:31,  1.16s/it]
 68%|██████▊   | 46286/67700 [27:49:42<6:28:41,  1.09s/it]
 68%|██████▊   | 46287/67700 [27:49:45<9:10:09,  1.54s/it]
 68%|██████▊   | 46288/67700 [27:49:47<11:02:14,  1.86s/it]
 68%|██████▊   | 46289/67700 [27:49:50<12:09:54,  2.05s/it]
 68%|██████▊   | 46290/67700 [27:49:52<12:51:25,  2.16s/it]
 68%|██████▊   | 46291/67700 [27:49:54<13:15:53,  2.23s/it]
 68%|██████▊   | 46292/67700 [27:49:57<13:21:39,  2.25s/it]
 68%|██████▊   | 46293/67700 [27:49:59<13:20:40,  2.24s/it]
 68%|██████▊   | 46294/67700 [27:50:01<13:14:52,  2.23s/it]
 68%|██████▊   | 46295/67700 [27:50:03<13:06:27,  2.20s/it]
 68%|██████▊   | 46296/67700 [27:50:05<12:55:06,  2.17s/it]
 68%|██████▊   | 46297/67700 [27:50:07<12:49:15,  2.16s/it]
 68%|██████▊   | 46298/67700 [27:50:10<12:36:02,  2.12s/it]
 68%|██████▊   | 46299/67700 [27:50:12<12:27:04,  2.09s/it]
 68%|██████▊   | 46300/67700 [27:50:14<12:16:33,  2.07s/it]
                                                           
 68%|██████▊   | 46300/67700 [27:50:14<12:16:33,  2.07s/it]
 68%|██████▊   | 46301/67700 [27:50:16<12:14:40,  2.06s/it]
 68%|██████▊   | 46302/67700 [27:50:18<12:12:22,  2.05s/it]
 68%|██████▊   | 46303/67700 [27:50:20<12:07:19,  2.04s/it]
 68%|██████▊   | 46304/67700 [27:50:22<12:02:29,  2.03s/it]
 68%|██████▊   | 46305/67700 [27:50:24<11:58:59,  2.02s/it]
 68%|██████▊   | 46306/67700 [27:50:26<11:47:53,  1.99s/it]
 68%|██████▊   | 46307/67700 [27:50:27<11:40:08,  1.96s/it]
 68%|██████▊   | 46308/67700 [27:50:29<11:30:48,  1.94s/it]
 68%|██████▊   | 46309/67700 [27:50:31<11:23:23,  1.92s/it]
 68%|██████▊   | 46310/67700 [27:50:33<11:14:13,  1.89s/it]
 68%|██████▊   | 46311/67700 [27:50:35<11:02:47,  1.86s/it]
 68%|██████▊   | 46312/67700 [27:50:37<10:50:30,  1.82s/it]
 68%|██████▊   | 46313/67700 [27:50:38<10:43:22,  1.80s/it]
 68%|██████▊   | 46314/67700 [27:50:40<10:32:07,  1.77s/it]
 68%|██████▊   | 46315/67700 [27:50:42<10:25:23,  1.75s/it]
 68%|██████▊   | 46316/67700 [27:50:43<10:16:57,  1.73s/it]
 68%|██████▊   | 46317/67700 [27:50:45<10:10:11,  1.71s/it]
 68%|██████▊   | 46318/67700 [27:50:47<10:01:46,  1.69s/it]
 68%|██████▊   | 46319/67700 [27:50:48<9:53:35,  1.67s/it] 
 68%|██████▊   | 46320/67700 [27:50:50<9:42:12,  1.63s/it]
 68%|██████▊   | 46321/67700 [27:50:51<9:37:24,  1.62s/it]
 68%|██████▊   | 46322/67700 [27:50:53<9:29:45,  1.60s/it]
 68%|██████▊   | 46323/67700 [27:50:55<9:23:38,  1.58s/it]
 68%|██████▊   | 46324/67700 [27:50:56<9:14:17,  1.56s/it]
 68%|██████▊   | 46325/67700 [27:50:58<9:03:12,  1.52s/it]
 68%|██████▊   | 46326/67700 [27:50:59<8:51:14,  1.49s/it]
 68%|██████▊   | 46327/67700 [27:51:00<8:38:38,  1.46s/it]
 68%|██████▊   | 46328/67700 [27:51:02<8:28:45,  1.43s/it]
 68%|██████▊   | 46329/67700 [27:51:03<8:14:04,  1.39s/it]
 68%|██████▊   | 46330/67700 [27:51:04<8:07:05,  1.37s/it]
 68%|██████▊   | 46331/67700 [27:51:05<7:50:34,  1.32s/it]
 68%|██████▊   | 46332/67700 [27:51:07<7:37:01,  1.28s/it]
 68%|██████▊   | 46333/67700 [27:51:08<7:23:38,  1.25s/it]
 68%|██████▊   | 46334/67700 [27:51:09<7:09:04,  1.20s/it]
 68%|██████▊   | 46335/67700 [27:51:10<6:49:12,  1.15s/it]
 68%|██████▊   | 46336/67700 [27:51:11<6:30:14,  1.10s/it]
 68%|██████▊   | 46337/67700 [27:51:14<9:09:33,  1.54s/it]
 68%|██████▊   | 46338/67700 [27:51:16<10:54:23,  1.84s/it]
 68%|██████▊   | 46339/67700 [27:51:19<12:03:15,  2.03s/it]
 68%|██████▊   | 46340/67700 [27:51:21<12:45:32,  2.15s/it]
 68%|██████▊   | 46341/67700 [27:51:23<13:02:04,  2.20s/it]
 68%|██████▊   | 46342/67700 [27:51:26<13:16:42,  2.24s/it]
 68%|██████▊   | 46343/67700 [27:51:28<13:22:27,  2.25s/it]
 68%|██████▊   | 46344/67700 [27:51:30<13:19:51,  2.25s/it]
 68%|██████▊   | 46345/67700 [27:51:32<13:11:34,  2.22s/it]
 68%|██████▊   | 46346/67700 [27:51:34<13:06:53,  2.21s/it]
 68%|██████▊   | 46347/67700 [27:51:37<13:00:01,  2.19s/it]
 68%|██████▊   | 46348/67700 [27:51:39<12:53:16,  2.17s/it]
 68%|██████▊   | 46349/67700 [27:51:41<12:42:32,  2.14s/it]
 68%|██████▊   | 46350/67700 [27:51:43<12:35:33,  2.12s/it]
 68%|██████▊   | 46351/67700 [27:51:45<12:27:39,  2.10s/it]
 68%|██████▊   | 46352/67700 [27:51:47<12:24:16,  2.09s/it]
 68%|██████▊   | 46353/67700 [27:51:49<12:18:01,  2.07s/it]
 68%|██████▊   | 46354/67700 [27:51:51<12:11:09,  2.06s/it]
 68%|██████▊   | 46355/67700 [27:51:53<12:00:03,  2.02s/it]
 68%|██████▊   | 46356/67700 [27:51:55<11:46:52,  1.99s/it]
 68%|██████▊   | 46357/67700 [27:51:57<11:36:18,  1.96s/it]
 68%|██████▊   | 46358/67700 [27:51:59<11:21:54,  1.92s/it]
 68%|██████▊   | 46359/67700 [27:52:00<11:14:54,  1.90s/it]
 68%|██████▊   | 46360/67700 [27:52:02<11:05:11,  1.87s/it]
 68%|██████▊   | 46361/67700 [27:52:04<10:52:23,  1.83s/it]
 68%|██████▊   | 46362/67700 [27:52:06<10:43:22,  1.81s/it]
 68%|██████▊   | 46363/67700 [27:52:08<10:34:47,  1.79s/it]
 68%|██████▊   | 46364/67700 [27:52:09<10:25:25,  1.76s/it]
 68%|██████▊   | 46365/67700 [27:52:11<10:15:28,  1.73s/it]
 68%|██████▊   | 46366/67700 [27:52:13<10:08:29,  1.71s/it]
 68%|██████▊   | 46367/67700 [27:52:14<9:59:03,  1.68s/it] 
 68%|██████▊   | 46368/67700 [27:52:16<9:49:51,  1.66s/it]
 68%|██████▊   | 46369/67700 [27:52:17<9:41:46,  1.64s/it]
 68%|██████▊   | 46370/67700 [27:52:19<9:33:43,  1.61s/it]
 68%|██████▊   | 46371/67700 [27:52:20<9:26:47,  1.59s/it]
 68%|██████▊   | 46372/67700 [27:52:22<9:22:50,  1.58s/it]
 68%|██████▊   | 46373/67700 [27:52:23<9:10:25,  1.55s/it]
 68%|██████▊   | 46374/67700 [27:52:25<9:01:10,  1.52s/it]
 69%|██████▊   | 46375/67700 [27:52:26<8:52:58,  1.50s/it]
 69%|██████▊   | 46376/67700 [27:52:28<8:43:48,  1.47s/it]
 69%|██████▊   | 46377/67700 [27:52:29<8:33:44,  1.45s/it]
 69%|██████▊   | 46378/67700 [27:52:31<8:30:14,  1.44s/it]
 69%|██████▊   | 46379/67700 [27:52:32<8:16:50,  1.40s/it]
 69%|██████▊   | 46380/67700 [27:52:33<8:03:19,  1.36s/it]
 69%|██████▊   | 46381/67700 [27:52:34<7:49:31,  1.32s/it]
 69%|██████▊   | 46382/67700 [27:52:36<7:36:55,  1.29s/it]
 69%|██████▊   | 46383/67700 [27:52:37<7:30:14,  1.27s/it]
 69%|██████▊   | 46384/67700 [27:52:38<7:13:05,  1.22s/it]
 69%|██████▊   | 46385/67700 [27:52:39<6:52:50,  1.16s/it]
 69%|██████▊   | 46386/67700 [27:52:40<6:30:42,  1.10s/it]
 69%|██████▊   | 46387/67700 [27:52:43<9:09:35,  1.55s/it]
 69%|██████▊   | 46388/67700 [27:52:45<10:54:43,  1.84s/it]
 69%|██████▊   | 46389/67700 [27:52:48<11:59:48,  2.03s/it]
 69%|██████▊   | 46390/67700 [27:52:50<12:47:37,  2.16s/it]
 69%|██████▊   | 46391/67700 [27:52:52<13:14:51,  2.24s/it]
 69%|██████▊   | 46392/67700 [27:52:55<13:14:13,  2.24s/it]
 69%|██████▊   | 46393/67700 [27:52:57<13:07:03,  2.22s/it]
 69%|██████▊   | 46394/67700 [27:52:59<12:58:47,  2.19s/it]
 69%|██████▊   | 46395/67700 [27:53:01<12:59:46,  2.20s/it]
 69%|██████▊   | 46396/67700 [27:53:03<12:59:13,  2.19s/it]
 69%|██████▊   | 46397/67700 [27:53:06<12:58:37,  2.19s/it]
 69%|██████▊   | 46398/67700 [27:53:08<12:45:35,  2.16s/it]
 69%|██████▊   | 46399/67700 [27:53:10<12:38:42,  2.14s/it]
 69%|██████▊   | 46400/67700 [27:53:12<12:28:41,  2.11s/it]
                                                           
 69%|██████▊   | 46400/67700 [27:53:12<12:28:41,  2.11s/it]
 69%|██████▊   | 46401/67700 [27:53:14<12:22:34,  2.09s/it]
 69%|██████▊   | 46402/67700 [27:53:16<12:13:11,  2.07s/it]
 69%|██████▊   | 46403/67700 [27:53:18<12:03:05,  2.04s/it]
 69%|██████▊   | 46404/67700 [27:53:20<11:56:58,  2.02s/it]
 69%|██████▊   | 46405/67700 [27:53:22<11:50:27,  2.00s/it]
 69%|██████▊   | 46406/67700 [27:53:24<11:41:05,  1.98s/it]
 69%|██████▊   | 46407/67700 [27:53:25<11:29:42,  1.94s/it]
 69%|██████▊   | 46408/67700 [27:53:27<11:18:32,  1.91s/it]
 69%|██████▊   | 46409/67700 [27:53:29<11:11:18,  1.89s/it]
 69%|██████▊   | 46410/67700 [27:53:31<11:00:41,  1.86s/it]
 69%|██████▊   | 46411/67700 [27:53:33<10:51:42,  1.84s/it]
 69%|██████▊   | 46412/67700 [27:53:35<10:43:57,  1.82s/it]
 69%|██████▊   | 46413/67700 [27:53:36<10:35:44,  1.79s/it]
 69%|██████▊   | 46414/67700 [27:53:38<10:26:37,  1.77s/it]
 69%|██████▊   | 46415/67700 [27:53:40<10:18:42,  1.74s/it]
 69%|██████▊   | 46416/67700 [27:53:41<10:09:33,  1.72s/it]
 69%|██████▊   | 46417/67700 [27:53:43<10:04:58,  1.71s/it]
 69%|██████▊   | 46418/67700 [27:53:45<9:53:38,  1.67s/it] 
 69%|██████▊   | 46419/67700 [27:53:46<9:44:54,  1.65s/it]
 69%|██████▊   | 46420/67700 [27:53:48<9:36:23,  1.63s/it]
 69%|██████▊   | 46421/67700 [27:53:49<9:31:48,  1.61s/it]
 69%|██████▊   | 46422/67700 [27:53:51<9:20:12,  1.58s/it]
 69%|██████▊   | 46423/67700 [27:53:52<9:09:59,  1.55s/it]
 69%|██████▊   | 46424/67700 [27:53:54<9:02:11,  1.53s/it]
 69%|██████▊   | 46425/67700 [27:53:55<8:53:08,  1.50s/it]
 69%|██████▊   | 46426/67700 [27:53:57<8:43:13,  1.48s/it]
 69%|██████▊   | 46427/67700 [27:53:58<8:33:21,  1.45s/it]
 69%|██████▊   | 46428/67700 [27:53:59<8:23:13,  1.42s/it]
 69%|██████▊   | 46429/67700 [27:54:01<8:08:58,  1.38s/it]
 69%|██████▊   | 46430/67700 [27:54:02<7:56:40,  1.34s/it]
 69%|██████▊   | 46431/67700 [27:54:03<7:43:37,  1.31s/it]
 69%|██████▊   | 46432/67700 [27:54:04<7:29:28,  1.27s/it]
 69%|██████▊   | 46433/67700 [27:54:05<7:16:56,  1.23s/it]
 69%|██████▊   | 46434/67700 [27:54:07<7:00:55,  1.19s/it]
 69%|██████▊   | 46435/67700 [27:54:08<6:41:36,  1.13s/it]
 69%|██████▊   | 46436/67700 [27:54:08<6:19:03,  1.07s/it]
 69%|██████▊   | 46437/67700 [27:54:11<8:59:50,  1.52s/it]
 69%|██████▊   | 46438/67700 [27:54:14<10:47:25,  1.83s/it]
 69%|██████▊   | 46439/67700 [27:54:16<11:58:15,  2.03s/it]
 69%|██████▊   | 46440/67700 [27:54:19<12:51:03,  2.18s/it]
 69%|██████▊   | 46441/67700 [27:54:21<13:19:15,  2.26s/it]
 69%|██████▊   | 46442/67700 [27:54:23<13:33:53,  2.30s/it]
 69%|██████▊   | 46443/67700 [27:54:26<13:33:06,  2.30s/it]
 69%|██████▊   | 46444/67700 [27:54:28<13:21:58,  2.26s/it]
 69%|██████▊   | 46445/67700 [27:54:30<13:16:20,  2.25s/it]
 69%|██████▊   | 46446/67700 [27:54:32<13:14:23,  2.24s/it]
 69%|██████▊   | 46447/67700 [27:54:35<13:07:10,  2.22s/it]
 69%|██████▊   | 46448/67700 [27:54:37<12:55:38,  2.19s/it]
 69%|██████▊   | 46449/67700 [27:54:39<12:44:46,  2.16s/it]
 69%|██████▊   | 46450/67700 [27:54:41<12:38:27,  2.14s/it]
 69%|██████▊   | 46451/67700 [27:54:43<12:27:50,  2.11s/it]
 69%|██████▊   | 46452/67700 [27:54:45<12:19:28,  2.09s/it]
 69%|██████▊   | 46453/67700 [27:54:47<12:10:39,  2.06s/it]
 69%|██████▊   | 46454/67700 [27:54:49<12:01:55,  2.04s/it]
 69%|██████▊   | 46455/67700 [27:54:51<11:49:58,  2.01s/it]
 69%|██████▊   | 46456/67700 [27:54:53<11:37:45,  1.97s/it]
 69%|██████▊   | 46457/67700 [27:54:55<11:27:04,  1.94s/it]
 69%|██████▊   | 46458/67700 [27:54:56<11:15:09,  1.91s/it]
 69%|██████▊   | 46459/67700 [27:54:58<11:02:43,  1.87s/it]
 69%|██████▊   | 46460/67700 [27:55:00<10:50:03,  1.84s/it]
 69%|██████▊   | 46461/67700 [27:55:02<10:45:25,  1.82s/it]
 69%|██████▊   | 46462/67700 [27:55:04<10:36:36,  1.80s/it]
 69%|██████▊   | 46463/67700 [27:55:05<10:28:54,  1.78s/it]
 69%|██████▊   | 46464/67700 [27:55:07<10:21:28,  1.76s/it]
 69%|██████▊   | 46465/67700 [27:55:09<10:10:29,  1.72s/it]
 69%|██████▊   | 46466/67700 [27:55:10<10:03:21,  1.70s/it]
 69%|██████▊   | 46467/67700 [27:55:12<9:54:14,  1.68s/it] 
 69%|██████▊   | 46468/67700 [27:55:14<9:50:11,  1.67s/it]
 69%|██████▊   | 46469/67700 [27:55:15<9:40:03,  1.64s/it]
 69%|██████▊   | 46470/67700 [27:55:17<9:26:31,  1.60s/it]
 69%|██████▊   | 46471/67700 [27:55:18<9:15:57,  1.57s/it]
 69%|██████▊   | 46472/67700 [27:55:20<9:05:22,  1.54s/it]
 69%|██████▊   | 46473/67700 [27:55:21<9:03:57,  1.54s/it]
 69%|██████▊   | 46474/67700 [27:55:23<8:57:54,  1.52s/it]
 69%|██████▊   | 46475/67700 [27:55:24<8:49:04,  1.50s/it]
 69%|██████▊   | 46476/67700 [27:55:25<8:40:04,  1.47s/it]
 69%|██████▊   | 46477/67700 [27:55:27<8:26:41,  1.43s/it]
 69%|██████▊   | 46478/67700 [27:55:28<8:14:12,  1.40s/it]
 69%|██████▊   | 46479/67700 [27:55:29<7:59:59,  1.36s/it]
 69%|██████▊   | 46480/67700 [27:55:31<7:48:32,  1.32s/it]
 69%|██████▊   | 46481/67700 [27:55:32<7:36:18,  1.29s/it]
 69%|██████▊   | 46482/67700 [27:55:33<7:25:27,  1.26s/it]
 69%|██████▊   | 46483/67700 [27:55:34<7:15:11,  1.23s/it]
 69%|██████▊   | 46484/67700 [27:55:35<7:00:32,  1.19s/it]
 69%|██████▊   | 46485/67700 [27:55:36<6:43:11,  1.14s/it]
 69%|██████▊   | 46486/67700 [27:55:37<6:22:53,  1.08s/it]
 69%|██████▊   | 46487/67700 [27:55:40<8:57:58,  1.52s/it]
 69%|██████▊   | 46488/67700 [27:55:42<10:50:22,  1.84s/it]
 69%|██████▊   | 46489/67700 [27:55:45<11:59:39,  2.04s/it]
 69%|██████▊   | 46490/67700 [27:55:47<12:41:10,  2.15s/it]
 69%|██████▊   | 46491/67700 [27:55:50<13:12:56,  2.24s/it]
 69%|██████▊   | 46492/67700 [27:55:52<13:22:55,  2.27s/it]
 69%|██████▊   | 46493/67700 [27:55:54<13:25:02,  2.28s/it]
 69%|██████▊   | 46494/67700 [27:55:57<13:19:03,  2.26s/it]
 69%|██████▊   | 46495/67700 [27:55:59<13:15:49,  2.25s/it]
 69%|██████▊   | 46496/67700 [27:56:01<13:05:29,  2.22s/it]
 69%|██████▊   | 46497/67700 [27:56:03<12:58:08,  2.20s/it]
 69%|██████▊   | 46498/67700 [27:56:05<12:55:07,  2.19s/it]
 69%|██████▊   | 46499/67700 [27:56:07<12:43:43,  2.16s/it]
 69%|██████▊   | 46500/67700 [27:56:09<12:34:22,  2.14s/it]
                                                           
 69%|██████▊   | 46500/67700 [27:56:09<12:34:22,  2.14s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 2021
+  Batch size = 8
+{'eval_loss': 0.8489089012145996, 'eval_wer': 0.8649183572488867, 'eval_cer': 0.22035735796024894, 'eval_runtime': 114.6545, 'eval_samples_per_second': 17.627, 'eval_steps_per_second': 2.207, 'epoch': 67.95}
+{'loss': 1.503, 'learning_rate': 2.46837899543379e-05, 'epoch': 68.09}
+{'loss': 1.5194, 'learning_rate': 2.4569634703196347e-05, 'epoch': 68.24}
+{'loss': 1.493, 'learning_rate': 2.4455479452054795e-05, 'epoch': 68.39}
+{'loss': 1.5327, 'learning_rate': 2.434132420091324e-05, 'epoch': 68.54}
+{'loss': 1.5199, 'learning_rate': 2.4227168949771687e-05, 'epoch': 68.69}
+
+
  0%|          | 0/253 [00:00<?, ?it/s]
+
  1%|          | 2/253 [00:00<00:42,  5.92it/s]
+
  1%|          | 3/253 [00:00<00:58,  4.27it/s]
+
  2%|▏         | 4/253 [00:00<01:03,  3.93it/s]
+
  2%|▏         | 5/253 [00:01<01:09,  3.55it/s]
+
  2%|▏         | 6/253 [00:01<01:11,  3.46it/s]
+
  3%|▎         | 7/253 [00:01<01:15,  3.25it/s]
+
  3%|▎         | 8/253 [00:02<01:17,  3.15it/s]
+
  4%|▎         | 9/253 [00:02<01:18,  3.09it/s]
+
  4%|▍         | 10/253 [00:02<01:19,  3.04it/s]
+
  4%|▍         | 11/253 [00:03<01:20,  3.00it/s]
+
  5%|▍         | 12/253 [00:03<01:18,  3.05it/s]
+
  5%|▌         | 13/253 [00:03<01:20,  2.99it/s]
+
  6%|▌         | 14/253 [00:04<01:16,  3.13it/s]
+
  6%|▌         | 15/253 [00:04<01:18,  3.03it/s]
+
  6%|▋         | 16/253 [00:04<01:19,  3.00it/s]
+
  7%|▋         | 17/253 [00:05<01:21,  2.90it/s]
+
  7%|▋         | 18/253 [00:05<01:20,  2.94it/s]
+
  8%|▊         | 19/253 [00:05<01:17,  3.04it/s]
+
  8%|▊         | 20/253 [00:06<01:14,  3.14it/s]
+
  8%|▊         | 21/253 [00:06<01:16,  3.05it/s]
+
  9%|▊         | 22/253 [00:06<01:16,  3.00it/s]
+
  9%|▉         | 23/253 [00:07<01:17,  2.95it/s]
+
  9%|▉         | 24/253 [00:07<01:16,  3.00it/s]
+
 10%|▉         | 25/253 [00:07<01:16,  2.99it/s]
+
 10%|█         | 26/253 [00:08<01:16,  2.98it/s]
+
 11%|█         | 27/253 [00:08<01:17,  2.93it/s]
+
 11%|█         | 28/253 [00:08<01:15,  2.97it/s]
+
 11%|█▏        | 29/253 [00:09<01:20,  2.79it/s]
+
 12%|█▏        | 30/253 [00:09<01:19,  2.81it/s]
+
 12%|█▏        | 31/253 [00:10<01:17,  2.86it/s]
+
 13%|█▎        | 32/253 [00:10<01:18,  2.83it/s]
+
 13%|█▎        | 33/253 [00:10<01:16,  2.87it/s]
+
 13%|█▎        | 34/253 [00:11<01:16,  2.88it/s]
+
 14%|█▍        | 35/253 [00:11<01:15,  2.90it/s]
+
 14%|█▍        | 36/253 [00:11<01:11,  3.02it/s]
+
 15%|█▍        | 37/253 [00:12<01:10,  3.08it/s]
+
 15%|█▌        | 38/253 [00:12<01:12,  2.95it/s]
+
 15%|█▌        | 39/253 [00:12<01:11,  3.01it/s]
+
 16%|█▌        | 40/253 [00:13<01:08,  3.12it/s]
+
 16%|█▌        | 41/253 [00:13<01:08,  3.08it/s]
+
 17%|█▋        | 42/253 [00:13<01:09,  3.05it/s]
+
 17%|█▋        | 43/253 [00:13<01:05,  3.19it/s]
+
 17%|█▋        | 44/253 [00:14<01:07,  3.09it/s]
+
 18%|█▊        | 45/253 [00:14<01:08,  3.05it/s]
+
 18%|█▊        | 46/253 [00:14<01:05,  3.17it/s]
+
 19%|█▊        | 47/253 [00:15<01:06,  3.12it/s]
+
 19%|█▉        | 48/253 [00:15<01:05,  3.12it/s]
+
 19%|█▉        | 49/253 [00:15<01:04,  3.17it/s]
+
 20%|█▉        | 50/253 [00:16<01:04,  3.16it/s]
+
 20%|██        | 51/253 [00:16<01:05,  3.07it/s]
+
 21%|██        | 52/253 [00:16<01:06,  3.04it/s]
+
 21%|██        | 53/253 [00:17<01:05,  3.06it/s]
+
 21%|██▏       | 54/253 [00:17<01:05,  3.03it/s]
+
 22%|██▏       | 55/253 [00:17<01:03,  3.10it/s]
+
 22%|██▏       | 56/253 [00:18<01:04,  3.06it/s]
+
 23%|██▎       | 57/253 [00:18<01:02,  3.15it/s]
+
 23%|██▎       | 58/253 [00:18<01:02,  3.13it/s]
+
 23%|██▎       | 59/253 [00:19<01:02,  3.11it/s]
+
 24%|██▎       | 60/253 [00:19<01:00,  3.17it/s]
+
 24%|██▍       | 61/253 [00:19<01:02,  3.10it/s]
+
 25%|██▍       | 62/253 [00:20<00:59,  3.21it/s]
+
 25%|██▍       | 63/253 [00:20<01:00,  3.14it/s]
+
 25%|██▌       | 64/253 [00:20<01:00,  3.11it/s]
+
 26%|██▌       | 65/253 [00:21<01:00,  3.10it/s]
+
 26%|██▌       | 66/253 [00:21<01:01,  3.02it/s]
+
 26%|██▋       | 67/253 [00:21<01:03,  2.91it/s]
+
 27%|██▋       | 68/253 [00:22<01:01,  3.01it/s]
+
 27%|██▋       | 69/253 [00:22<00:59,  3.08it/s]
+
 28%|██▊       | 70/253 [00:22<00:57,  3.20it/s]
+
 28%|██▊       | 71/253 [00:23<01:00,  3.03it/s]
+
 28%|██▊       | 72/253 [00:23<00:57,  3.14it/s]
+
 29%|██▉       | 73/253 [00:23<00:56,  3.19it/s]
+
 29%|██▉       | 74/253 [00:23<00:57,  3.10it/s]
+
 30%|██▉       | 75/253 [00:24<00:57,  3.08it/s]
+
 30%|███       | 76/253 [00:24<00:58,  3.03it/s]
+
 30%|███       | 77/253 [00:24<00:57,  3.04it/s]
+
 31%|███       | 78/253 [00:25<00:58,  3.00it/s]
+
 31%|███       | 79/253 [00:25<00:59,  2.94it/s]
+
 32%|███▏      | 80/253 [00:26<00:59,  2.90it/s]
+
 32%|███▏      | 81/253 [00:26<00:58,  2.92it/s]
+
 32%|███▏      | 82/253 [00:26<00:55,  3.11it/s]
+
 33%|███▎      | 83/253 [00:26<00:53,  3.17it/s]
+
 33%|███▎      | 84/253 [00:27<00:54,  3.08it/s]
+
 34%|███▎      | 85/253 [00:27<00:55,  3.01it/s]
+
 34%|███▍      | 86/253 [00:27<00:53,  3.14it/s]
+
 34%|███▍      | 87/253 [00:28<00:53,  3.11it/s]
+
 35%|███▍      | 88/253 [00:28<00:50,  3.25it/s]
+
 35%|███▌      | 89/253 [00:28<00:52,  3.14it/s]
+
 36%|███▌      | 90/253 [00:29<00:52,  3.11it/s]
+
 36%|███▌      | 91/253 [00:29<00:51,  3.14it/s]
+
 36%|███▋      | 92/253 [00:29<00:51,  3.12it/s]
+
 37%|███▋      | 93/253 [00:30<00:53,  3.02it/s]
+
 37%|███▋      | 94/253 [00:30<00:51,  3.07it/s]
+
 38%|███▊      | 95/253 [00:30<00:50,  3.15it/s]
+
 38%|███▊      | 96/253 [00:31<00:49,  3.16it/s]
+
 38%|███▊      | 97/253 [00:31<00:50,  3.09it/s]
+
 39%|███▊      | 98/253 [00:31<00:49,  3.11it/s]
+
 39%|███▉      | 99/253 [00:32<00:51,  3.00it/s]
+
 40%|███▉      | 100/253 [00:32<00:49,  3.06it/s]
+
 40%|███▉      | 101/253 [00:32<00:48,  3.12it/s]
+
 40%|████      | 102/253 [00:33<00:48,  3.13it/s]
+
 41%|████      | 103/253 [00:33<00:49,  3.04it/s]
+
 41%|████      | 104/253 [00:33<00:48,  3.10it/s]
+
 42%|████▏     | 105/253 [00:34<00:47,  3.10it/s]
+
 42%|████▏     | 106/253 [00:34<00:45,  3.21it/s]
+
 42%|████▏     | 107/253 [00:34<00:42,  3.43it/s]
+
 43%|████▎     | 108/253 [00:34<00:44,  3.27it/s]
+
 43%|████▎     | 109/253 [00:35<00:41,  3.43it/s]
+
 43%|████▎     | 110/253 [00:35<00:42,  3.37it/s]
+
 44%|████▍     | 111/253 [00:35<00:43,  3.25it/s]
+
 44%|████▍     | 112/253 [00:36<00:43,  3.23it/s]
+
 45%|████▍     | 113/253 [00:36<00:43,  3.19it/s]
+
 45%|████▌     | 114/253 [00:36<00:44,  3.10it/s]
+
 45%|████▌     | 115/253 [00:37<00:43,  3.14it/s]
+
 46%|████▌     | 116/253 [00:37<00:44,  3.06it/s]
+
 46%|████▌     | 117/253 [00:37<00:44,  3.05it/s]
+
 47%|████▋     | 118/253 [00:38<00:42,  3.18it/s]
+
 47%|████▋     | 119/253 [00:38<00:42,  3.19it/s]
+
 47%|████▋     | 120/253 [00:38<00:43,  3.04it/s]
+
 48%|████▊     | 121/253 [00:39<00:43,  3.03it/s]
+
 48%|████▊     | 122/253 [00:39<00:40,  3.23it/s]
+
 49%|████▊     | 123/253 [00:39<00:41,  3.15it/s]
+
 49%|████▉     | 124/253 [00:40<00:41,  3.10it/s]
+
 49%|████▉     | 125/253 [00:40<00:41,  3.05it/s]
+
 50%|████▉     | 126/253 [00:40<00:41,  3.04it/s]
+
 50%|█████     | 127/253 [00:41<00:42,  2.97it/s]
+
 51%|█████     | 128/253 [00:41<00:41,  3.00it/s]
+
 51%|█████     | 129/253 [00:41<00:42,  2.91it/s]
+
 51%|█████▏    | 130/253 [00:42<00:43,  2.83it/s]
+
 52%|█████▏    | 131/253 [00:42<00:42,  2.86it/s]
+
 52%|█████▏    | 132/253 [00:42<00:40,  3.00it/s]
+
 53%|█████▎    | 133/253 [00:43<00:40,  2.99it/s]
+
 53%|█████▎    | 134/253 [00:43<00:39,  2.99it/s]
+
 53%|█████▎    | 135/253 [00:43<00:39,  2.98it/s]
+
 54%|█████▍    | 136/253 [00:44<00:38,  3.04it/s]
+
 54%|█████▍    | 137/253 [00:44<00:38,  3.00it/s]
+
 55%|█████▍    | 138/253 [00:44<00:38,  3.00it/s]
+
 55%|█████▍    | 139/253 [00:45<00:38,  2.98it/s]
+
 55%|█████▌    | 140/253 [00:45<00:37,  3.00it/s]
+
 56%|█████▌    | 141/253 [00:45<00:37,  2.98it/s]
+
 56%|█████▌    | 142/253 [00:46<00:36,  3.08it/s]
+
 57%|█████▋    | 143/253 [00:46<00:37,  2.92it/s]
+
 57%|█████▋    | 144/253 [00:46<00:36,  3.02it/s]
+
 57%|█████▋    | 145/253 [00:47<00:35,  3.01it/s]
+
 58%|█████▊    | 146/253 [00:47<00:36,  2.97it/s]
+
 58%|█████▊    | 147/253 [00:47<00:35,  2.95it/s]
+
 58%|█████▊    | 148/253 [00:48<00:34,  3.02it/s]
+
 59%|█████▉    | 149/253 [00:48<00:34,  2.98it/s]
+
 59%|█████▉    | 150/253 [00:48<00:33,  3.07it/s]
+
 60%|█████▉    | 151/253 [00:49<00:32,  3.14it/s]
+
 60%|██████    | 152/253 [00:49<00:32,  3.06it/s]
+
 60%|██████    | 153/253 [00:49<00:33,  2.98it/s]
+
 61%|██████    | 154/253 [00:50<00:32,  3.07it/s]
+
 61%|██████▏   | 155/253 [00:50<00:32,  3.05it/s]
+
 62%|██████▏   | 156/253 [00:50<00:32,  3.03it/s]
+
 62%|██████▏   | 157/253 [00:51<00:30,  3.11it/s]
+
 62%|██████▏   | 158/253 [00:51<00:30,  3.09it/s]
+
 63%|██████▎   | 159/253 [00:51<00:29,  3.23it/s]
+
 63%|██████▎   | 160/253 [00:51<00:29,  3.18it/s]
+
 64%|██████▎   | 161/253 [00:52<00:29,  3.09it/s]
+
 64%|██████▍   | 162/253 [00:52<00:30,  3.03it/s]
+
 64%|██████▍   | 163/253 [00:52<00:29,  3.06it/s]
+
 65%|██████▍   | 164/253 [00:53<00:28,  3.11it/s]
+
 65%|██████▌   | 165/253 [00:53<00:28,  3.06it/s]
+
 66%|██████▌   | 166/253 [00:53<00:28,  3.07it/s]
+
 66%|██████▌   | 167/253 [00:54<00:28,  3.03it/s]
+
 66%|██████▋   | 168/253 [00:54<00:26,  3.15it/s]
+
 67%|██████▋   | 169/253 [00:54<00:26,  3.19it/s]
+
 67%|██████▋   | 170/253 [00:55<00:26,  3.12it/s]
+
 68%|██████▊   | 171/253 [00:55<00:25,  3.20it/s]
+
 68%|██████▊   | 172/253 [00:55<00:24,  3.26it/s]
+
 68%|██████▊   | 173/253 [00:56<00:23,  3.33it/s]
+
 69%|██████▉   | 174/253 [00:56<00:25,  3.04it/s]
+
 69%|██████▉   | 175/253 [00:56<00:24,  3.17it/s]
+
 70%|██████▉   | 176/253 [00:57<00:23,  3.27it/s]
+
 70%|██████▉   | 177/253 [00:57<00:24,  3.14it/s]
+
 70%|███████   | 178/253 [00:57<00:23,  3.15it/s]
+
 71%|███████   | 179/253 [00:58<00:24,  3.06it/s]
+
 71%|███████   | 180/253 [00:58<00:24,  3.03it/s]
+
 72%|███████▏  | 181/253 [00:58<00:23,  3.07it/s]
+
 72%|███████▏  | 182/253 [00:59<00:23,  2.99it/s]
+
 72%|███████▏  | 183/253 [00:59<00:22,  3.05it/s]
+
 73%|███████▎  | 184/253 [00:59<00:23,  2.95it/s]
+
 73%|███████▎  | 185/253 [01:00<00:22,  2.97it/s]
+
 74%|███████▎  | 186/253 [01:00<00:22,  2.99it/s]
+
 74%|███████▍  | 187/253 [01:00<00:22,  3.00it/s]
+
 74%|███████▍  | 188/253 [01:01<00:21,  3.01it/s]
+
 75%|███████▍  | 189/253 [01:01<00:20,  3.14it/s]
+
 75%|███████▌  | 190/253 [01:01<00:20,  3.04it/s]
+
 75%|███████▌  | 191/253 [01:02<00:21,  2.94it/s]
+
 76%|███████▌  | 192/253 [01:02<00:20,  3.00it/s]
+
 76%|███████▋  | 193/253 [01:02<00:19,  3.15it/s]
+
 77%|███████▋  | 194/253 [01:02<00:18,  3.11it/s]
+
 77%|███████▋  | 195/253 [01:03<00:18,  3.13it/s]
+
 77%|███████▋  | 196/253 [01:03<00:18,  3.06it/s]
+
 78%|███████▊  | 197/253 [01:03<00:17,  3.15it/s]
+
 78%|███████▊  | 198/253 [01:04<00:17,  3.08it/s]
+
 79%|███████▊  | 199/253 [01:04<00:18,  2.95it/s]
+
 79%|███████▉  | 200/253 [01:05<00:18,  2.89it/s]
+
 79%|███████▉  | 201/253 [01:05<00:17,  2.94it/s]
+
 80%|███████▉  | 202/253 [01:05<00:17,  2.97it/s]
+
 80%|████████  | 203/253 [01:05<00:16,  3.02it/s]
+
 81%|████████  | 204/253 [01:06<00:16,  2.96it/s]
+
 81%|████████  | 205/253 [01:06<00:16,  2.94it/s]
+
 81%|████████▏ | 206/253 [01:07<00:16,  2.88it/s]
+
 82%|████████▏ | 207/253 [01:07<00:15,  2.91it/s]
+
 82%|████████▏ | 208/253 [01:07<00:15,  2.89it/s]
+
 83%|████████▎ | 209/253 [01:08<00:15,  2.89it/s]
+
 83%|████████▎ | 210/253 [01:08<00:14,  2.99it/s]
+
 83%|████████▎ | 211/253 [01:08<00:14,  2.94it/s]
+
 84%|████████▍ | 212/253 [01:09<00:14,  2.86it/s]
+
 84%|████████▍ | 213/253 [01:09<00:13,  2.88it/s]
+
 85%|████████▍ | 214/253 [01:09<00:13,  2.87it/s]
+
 85%|████████▍ | 215/253 [01:10<00:13,  2.91it/s]
+
 85%|████████▌ | 216/253 [01:10<00:12,  2.96it/s]
+
 86%|████████▌ | 217/253 [01:10<00:11,  3.06it/s]
+
 86%|████████▌ | 218/253 [01:11<00:11,  3.06it/s]
+
 87%|████████▋ | 219/253 [01:11<00:11,  3.04it/s]
+
 87%|████████▋ | 220/253 [01:11<00:11,  2.93it/s]
+
 87%|████████▋ | 221/253 [01:12<00:10,  2.91it/s]
+
 88%|████████▊ | 222/253 [01:12<00:10,  2.93it/s]
+
 88%|████████▊ | 223/253 [01:12<00:10,  2.94it/s]
+
 89%|████████▊ | 224/253 [01:13<00:09,  3.01it/s]
+
 89%|████████▉ | 225/253 [01:13<00:09,  2.97it/s]
+
 89%|████████▉ | 226/253 [01:13<00:08,  3.01it/s]
+
 90%|████████▉ | 227/253 [01:14<00:08,  3.12it/s]
+
 90%|█████████ | 228/253 [01:14<00:08,  3.09it/s]
+
 91%|█████████ | 229/253 [01:14<00:07,  3.06it/s]
+
 91%|█████████ | 230/253 [01:15<00:07,  3.03it/s]
+
 91%|█████████▏| 231/253 [01:15<00:07,  2.99it/s]
+
 92%|█████████▏| 232/253 [01:15<00:06,  3.02it/s]
+
 92%|█████████▏| 233/253 [01:16<00:06,  3.03it/s]
+
 92%|█████████▏| 234/253 [01:16<00:06,  3.06it/s]
+
 93%|█████████▎| 235/253 [01:16<00:05,  3.21it/s]
+
 93%|█████████▎| 236/253 [01:17<00:05,  3.21it/s]
+
 94%|█████████▎| 237/253 [01:17<00:04,  3.21it/s]
+
 94%|█████████▍| 238/253 [01:17<00:04,  3.00it/s]
+
 94%|█████████▍| 239/253 [01:18<00:04,  3.05it/s]
+
 95%|█████████▍| 240/253 [01:18<00:04,  3.00it/s]
+
 95%|█████████▌| 241/253 [01:18<00:04,  2.94it/s]
+
 96%|█████████▌| 242/253 [01:19<00:03,  2.84it/s]
+
 96%|█████████▌| 243/253 [01:19<00:03,  2.80it/s]
+
 96%|█████████▋| 244/253 [01:19<00:03,  2.79it/s]
+
 97%|█████████▋| 245/253 [01:20<00:02,  2.89it/s]
+
 97%|█████████▋| 246/253 [01:20<00:02,  2.86it/s]
+
 98%|█████████▊| 247/253 [01:20<00:02,  2.87it/s]
+
 98%|█████████▊| 248/253 [01:21<00:01,  2.77it/s]
+
 98%|█████████▊| 249/253 [01:21<00:01,  2.84it/s]
+
 99%|█████████▉| 250/253 [01:21<00:01,  2.88it/s]
+
 99%|█████████▉| 251/253 [01:22<00:00,  2.96it/s]
+
+
                                                           
+
                                                 
 69%|██████▊   | 46500/67700 [27:58:04<12:34:22,  2.14s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-46500
+Configuration saved in ./checkpoint-46500/config.json
+Model weights saved in ./checkpoint-46500/pytorch_model.bin
+Configuration saved in ./checkpoint-46500/preprocessor_config.json
+Configuration saved in ./preprocessor_config.json

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba4a99e58145f5b2ebf2c1ddb2f9693eb7fdd0c6337c12e88fcc4127be62d6b
+oid sha256:e8d31ed69630d40de6f00b6c01a3689781dbd0caee2935467a5496f665b4d204
 size 1280898545

runs/Feb06_10-51-19_job-aa543290-d6de-4d4d-8a32-2149b1b8e7e3/events.out.tfevents.1644145311.job-aa543290-d6de-4d4d-8a32-2149b1b8e7e3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b123bf26acede9ea51ed425ac5f11fb937020e3f72b81ba6f45fdfd1c8d363
-size 111795
+oid sha256:9c419d47187d32baefd827424d72c45ced843142be6b885e8d896bbe88f28a2d
+size 112967